Radio‐Frequency Linear Analysis and Optimization of Silicon Photonic Neural Networks

Broadband analog signal processors utilizing silicon photonics have demonstrated a significant impact in numerous application spaces, offering unprecedented bandwidths, dynamic range, and tunability. In the past decade, microwave photonic techniques have been applied to neuromorphic processing, resulting in the development of novel photonic neural network architectures. Neuromorphic photonic systems can enable machine learning capabilities at extreme bandwidths and speeds. Herein, low‐quality factor microring resonators are implemented to demonstrate broadband optical weighting. In addition, silicon photonic neural network architectures are critically evaluated, simulated, and optimized from a radio‐frequency performance perspective. This analysis highlights the linear front‐end of the photonic neural network, the effects of linear and nonlinear loss within silicon waveguides, and the impact of electrical preamplification. Silicon PNNs have demonstrated analog processing with unprecedented bandwidths, dynamic range, and scalability. Herein, the authors demonstrate broadband linear operation, high‐speed analysis, and optimization. The radio‐frequency analysis highlights the linear front‐end, nonlinear back‐end, the effects of linear and nonlinear silicon waveguide loss, and the impact of low‐noise preamplification.